AI improvement prompts

Paano ito gumagana

Dalawang piraso ng data ang nagsasama sa pag-click:

• Ang finding — title, description, evidence, remediation, CWE — naka-load na kasama ng report.
• Ang framework ng codebase mo — nade-detect mula sa discovery.tech-fingerprint findings ng scan (Next.js, React, Vue, Django, Express, Rails, Laravel, Flask). Nagfa-fallback sa generic recipe kapag walang framework na na-detect (pagkatapos ay hihilingin ng agent prompt sa LLM na i-detect ito mula sa repo state).

Templates live in lib/scanner/fix-prompts.ts. The registry has check-specific guidance for crawlability, search presentation, semantic content, structured data, media, performance, accessibility, forms, mobile/i18n, runtime, owner journeys, and repo-quality issues. For everything else, the existing remediation field on the finding becomes the generic recipe.

Ano ang hitsura ng prompt

Fix the "Hero image is lazy-loaded and missing dimensions" finding on /pricing.

Issue: The largest above-the-fold image is marked loading="lazy" and has
no explicit width/height. That can delay LCP and create layout shift.

Codebase context: Next.js.

Recommended fix:
Use next/image or the existing image component with explicit width/height,
responsive sizes, meaningful alt text, and priority/fetchPriority for the
first major visual on the page.

Constraints:
- Don't break existing tests; run the test suite after the change.
- Match the codebase's existing style and lint config.
- Add a brief comment explaining the performance reasoning only where the
  fix would otherwise look arbitrary.
- If the fix needs a new dependency, install it via the project's
  package manager (npm / pnpm / pip / bundle / composer).

Reference: Core Web Vitals / Largest Contentful Paint guidance.

Sinusuportahang frameworks

Nagpapakita kami ng framework-specific snippets para sa:

• Next.js, React, Vue, Nuxt, Svelte (frontend)
• Express, Fastify (Node.js backend)
• Django, Flask (Python)
• Ruby on Rails
• Laravel (PHP)
• ASP.NET Core (planned, fallback sa generic sa ngayon)

Best-effort ang framework detection. Sini-sniff namin ang __NEXT_DATA__ tags, __NUXT__, hash cookies (laravel_session), X-Powered-By headers, at ilang iba pang signals. Kung custom framework ang gamit mo, magfa-fallback ang prompt sa generic recipe at aalamin ito ng agent mula sa iyong package.json.

Gamitin ito mula sa AI agent mo

Kung na-wire mo na ang MCP server, naka-expose ang parehong prompt bilang slash command. Mula sa Claude Desktop:

/fixweb-fix finding_id=550e8400-e29b-41d4-a716-446655440000

The renderer looks up the finding, detects the framework from the parent scan when available, renders the templated prompt, and injects it into your conversation as the user message. No round-trip to our Claude API; templates are pure and free.

Bakit hindi namin tinatawag ang Claude sa bawat click

Noong launch, pinag-isipan naming tawagin ang Anthropic API sa bawat click para pinuhin ang prompt gamit ang codebase context. Hindi namin ginawa, dahil:

• Ang agent na pinapasukan ng user sa pamamagitan ng paste ay mayroon na ng codebase context — ginagamit nila ang Cursor / Claude Desktop habang bukas ang repo nila.
• Ang templating kada-(check × framework) ay sumasaklaw sa ~80% ng value nang walang per-click cost.
• Maaaring magpaandar ng API mamaya ang opt-in na “Refine with AI for my codebase” kung gusto ito ng users. Sa ngayon, hindi.